<\/p>\n
Damaris<\/em> is a middleware for asynchronous I\/O and data management targeting large-scale, MPI-based HPC simulations. It initially proposed to dedicate cores for asynchronous I\/O in multicore nodes of recent HPC platforms, with an emphasis on ease of integration in existing simulations, efficient resource usage (with the use of shared memory) and simplicity of extension through plug-ins. To get started, have a look at the following pages: Instrumenting a Simulation<\/a> and Data Description<\/a>. These pages introduce the C and FORTRAN client side API and the XML configuration file to configure Damaris<\/em> and describe the data being passed through to its server side processing plugins.<\/p>\n To access the Damaris source code<\/em>, it is available here: https:\/\/gitlab.inria.fr\/Damaris\/damaris<\/a>. You can then follow the instructions for the Damaris Compilation<\/a> and once compiled and installed, try running one of the many example codes<\/a>.<\/p>\n If writing your own plugin<\/em> for use with Damaris then a deep dive into the C++ API available can be accessed through the dOxygen reference<\/a> pages. Be sure to look at the already available plugins for examples of how to access data (e.g. HDF5<\/a>) on the Damaris server side processes. Typically, you need to loop over Variables<\/a>, and then from the Variables you need to access their Damaris<\/em> was at the core of the PhD thesis of Matthieu Dorier<\/a>, who received an Accessit to the Gilles Kahn Ph.D. Thesis Award of the SIF and the Academy of Science in 2015. Developed in the framework of our collaboration with the JLESC – Joint Laboratory for Extreme-Scale Computing<\/a>,<\/b> Damaris<\/em> was the first software resulted from this joint lab validated in 2011 for integration to the Blue Waters supercomputer project. It scaled up to 16,000 cores on Oak Ridge\u2019s leadership supercomputer Titan<\/a> (first in the Top500 supercomputer list in 2013) before being validated on other top supercomputers. Active development is currently continuing within the KerData<\/a> team at Inria, where it is at the center of several collaborations with industry as well as with national and international academic partners.<\/p>\n Most HPC simulations work through a series of iterations, generating a large dataset on each iteration, as a result:<\/p>\n As a solution to the mentioned problem, Damaris<\/em>, that is a middleware for data management targeting large-scale, HPC simulations is designed. HPC simulations can benefit from Damaris<\/em> by:<\/p>\n Any HPC simulation can benefit from Damaris<\/em> for its I\/O optimization:<\/p>\n Those simulation applications that model complex structures, dynamics, phenomena or behaviors, in order to predict their specific concerns to the highest possible degree of precision, can be considered as a beneficiary of Damaris<\/em>.<\/p>\n The following technologies has been adopted for development, benchmarking and validation of Damaris<\/em>:<\/p>\n <\/p>","protected":false},"excerpt":{"rendered":" Damaris is a middleware for asynchronous I\/O and data management targeting large-scale, MPI-based HPC simulations. It initially proposed to dedicate cores for asynchronous I\/O in multicore nodes of recent HPC platforms, with an emphasis on ease of integration in existing simulations, efficient resource usage (with the use of shared memory)…<\/p>\n
\nOver the years, Damaris<\/em> has evolved into a more elaborate system, providing the possibility to use dedicated cores or dedicated nodes to carry out in situ data processing and visualization. It proposes a seamless connection to various I\/O and visualization libraries, including HDF5, Paraview, and Visit, and allows the integration of Python based access to data presented via the Damaris API, allowing, for example, Ascent based in situ visualizations, or Dask based processing of data, all with a minimal impact on run time. Damaris<\/em> provides an extremely simple API<\/abbr> and can be easily integrated into existing large-scale simulations.<\/p>\n<\/div>\nGet started with Damaris<\/h3>\n
Short History<\/h3>\n
Why Damaris?<\/h3>\n
\n
Solution<\/h3>\n
\n
Benefits<\/h3>\n
\n
Use Cases<\/h3>\n
\n
Technologies<\/h3>\n
\n